Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    額
    -0.08
     circul
    -0.08
     circulación
    -0.08
    מר
    -0.08
    !!!!
    -0.07
     indiqué
    -0.07
    なし
    -0.07
     tambahan
    -0.07
     frc
    -0.07
     unrest
    -0.07
    POSITIVE LOGITS
     retrospect
    0.14
     nostalg
    0.12
     retrospective
    0.12
     hindsight
    0.12
    昔
    0.12
     antigos
    0.11
    过去
    0.11
     vergang
    0.11
     الماضي
    0.11
     прошлого
    0.11
    Act Density 0.053%

    No Known Activations